These configs contain the architecture settings required to run inference/training/finetuning on the LLaMA model suite.

LLaMA finetuning can be launched with

python ./deepy.py ./train.py -d configs llama/7B.yml llama/train_config.yml local_setup.yml

If training from scratch, set finetune=False in ./configs/llama/train_config.yml.

LLaMA generation can be launched with

python ./deepy.py ./generate.py -d configs  \
  llama/7B.yml llama/train_config.yml local_setup.yml text_generation.yml \
  -i input_prompt.txt -o prompt_out.txt